agent-emacs

Unified persistent text-based environment for AI agents. Use when an agent needs to maintain state across sessions, perform structural code editing, or manage remote nodes via TRAMP. Transforms the agent from a stateless script executor into a stateful resident of a living Emacs daemon.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "agent-emacs" with this command: npx skills add PiTZE/agent-emacs

Agent Emacs: The Living Workspace

This skill provides a persistent, high-performance Emacs environment designed specifically for AI agents. It replaces fragmented CLI tools with a unified "Living Image" workflow.

Core Concepts

  1. The Daemon: All work happens inside a persistent Emacs daemon (emacs-agent.service).
  2. The Socket: Communication is handled via emacsclient -s /tmp/emacs0/server.
  3. Buffers as State: Files, terminal outputs, and remote connections are treated as persistent buffers. State is maintained between agent turns.

Operational Workflow

1. Structural Editing

Do not use regex for complex code changes. Use ELisp forms to manipulate the AST.

emacsclient -s /tmp/emacs0/server --eval "(with-current-buffer \"main.lisp\" (goto-char (point-max)) (insert \"\n(new-function)\"))"

2. Remote Infrastructure (TRAMP)

Manage remote nodes transparently. Opening a remote file automatically establishes a persistent SSH tunnel.

(find-file "/ssh:user@remote-node:/etc/config.json")

3. Project Management (Magit)

Use Magit for all Git operations to ensure high-integrity commits and staging.

Advanced Workflows

For detailed patterns on recursive data processing (RLM), memory management, and REPL-based accuracy, see:

Guaranteed Accuracy

Always use the Emacs Lisp REPL for math, data manipulation, or status calculations. Accuracy is paramount; do not attempt manual calculations.

Initialization

Run scripts/bootstrap.sh to ensure the daemon is active and the agent-init.el configuration is loaded.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

Ai Freelancing Guide

Provides a complete guide to AI freelancing including niche analysis, pricing, client acquisition, proposal templates, and delivery workflows.

Registry SourceRecently Updated
Coding

Ai Code Assistant

提供多语言AI智能代码处理与批量自动化,显著提升开发效率,适合企业、团队及自由职业者。

Registry SourceRecently Updated
Coding

Life Control

Orchestrate the Life Control CLI skill for OpenClaw agent fleets: initialize the Life Control database, register agent personas, wire Telegram bots, and run daily routines (Morning Alignment, Body Protocol, Financial Pulse, Social Radar, Work Priming, Shutdown). Use when a user asks to create or run a Life Control system, OpenClaw skill integration, or agent persona automation for personal life tracking.

Registry SourceRecently Updated